JP5911981B2 - Document search apparatus, method and program - Google Patents

Description

  Embodiments described herein relate generally to a document search apparatus, method, and program.

  2. Description of the Related Art A document search apparatus that searches a database for a handwritten document that is similar to or matches a handwritten query input or specified by a user is known.

Cheng Cheng, Bilan Zhu, Masaki Nakagawa: "A Discriminative Model for On-line Handwritten Japanese Text Retrieval", International Conference on Document Analysis and Recognition, 2011 Pasitthideth LUANGVILAY, Bilan ZHU, Masaki NAKAGAWA: "An On-line Handwritten Text Search Method based on Directional Feature Matching", International Conference on Document Analysis and Recognition, 2011

  It is desirable that an accurate search can be performed by a search method according to the type of query.

  According to the embodiment, there is provided a document search apparatus including an acquisition unit that acquires handwriting data, a determination unit that determines a type of query, a search unit that searches for a document, and a display unit that displays a search result. Provided. The acquisition unit acquires handwriting data including coordinate data. The determination unit determines the type of query by determining the shape of the handwriting based on the coordinate data. The retrieval unit obtains a retrieval result by retrieving a document according to a retrieval method corresponding to the type of query. The display unit displays the search result by a display method according to the type of the query.

1 is a block diagram of a document search apparatus according to an embodiment. The figure which shows the kind of query. The figure for demonstrating the input method of a query. The figure for demonstrating the distinction according to the direction of handwriting. The flowchart which shows the process of query determination. The flowchart which shows the process of shape determination. The flowchart which shows the process of closed loop determination. The figure which shows an ink data structure. The figure which shows the example of a display of a search result. 1 is a hardware configuration diagram of a document search apparatus according to an embodiment. The figure which shows an example of the system which shares handwritten document data via a network. The figure for demonstrating the process which determines whether a handwriting is contained inside a closed loop. The figure for demonstrating the process which determines whether there exists a handwriting in the vicinity upper part of a horizontal line.

Hereinafter, embodiments will be described with reference to the drawings.
The present embodiment relates to a search system when a search target and a query are handwritten data. In other words, this system is mainly a language-independent search system in which the search target is a “handwritten document” and the query used for the search is a query using handwritten characters (hereinafter referred to as “handwritten query”). Target. The handwritten query includes not only characters but also those drawn by the user such as marks and lines.

  However, the search target may be a text document. In this case, the handwritten query is converted into a text query and a search is performed. The search target may be a handwritten document, and the query used for the search may be a text query. In this case, the text query is converted into a handwritten query and a search is performed. In any system example, the type of the handwritten query is determined according to the embodiment described below, the search is executed by a search method according to the type of the handwritten query, and the search result is displayed by an appropriate display method according to the search method. To do.

  In the present embodiment, the breakdown of the types of handwritten queries is, for example, “character string”, “single stroke mark”, “underline”, and “border line”. Depending on the type of handwritten query, search targets in similar or matching handwritten documents differ. For example, when the type of handwritten query is a character string, the character string itself is a search target. In the case of a one-stroke mark, it is not only the case that one-stroke mark itself is to be searched. In the case of a single stroke mark, the search target is a character string before and after the single stroke mark. When the type of the handwritten query is an underline or a surrounding line, what is desired to be searched is a character string underlined or a character string surrounded by the surrounding line.

  Note that the type of handwritten query is not limited to the above. A person skilled in the art can change the embodiment by expanding the types of handwritten queries and conversely reducing the types of handwritten queries based on the present disclosure.

  As shown in FIG. 1, the document search apparatus according to the embodiment includes an acquisition unit 1 that acquires handwriting data, a query determination unit 2 that determines a type of query, a search unit 3 that searches for a document, and a handwritten document. A database (DB) 4 and a search result display unit 5 for displaying search results are provided.

  The acquisition unit 1 acquires handwriting data including coordinate data.

The handwriting data acquired by the acquisition unit 1 has time-series data of coordinates separated for each stroke (stroke), and is expressed as follows, for example.
Picture 1: (x (1,1), y (1,1)), (x (1,2), y (1,2)), ..., (x (1, N (1)), y ( 1, N (1)))
Picture 2: (x (2,1), y (2,1)), (x (2,2), y (2,2)), ..., (x (2, N (2)), y ( 2, N (2)))
...
N (i) is the number of points at the time of sampling i.
The handwritten document stored in the handwritten document DB 4 also has handwriting data as described above.

FIG. 2 shows the types of queries by legend. As described above, in this embodiment, the type of query is any one of a character string, a single stroke mark, an underline, and a surrounding line. These are classified according to the shape of the handwriting. In FIG. 2, the reference numeral 20 indicates a character string query. This is, for example, a character string “idea” input by handwriting (or selected in a handwritten document). It goes without saying that the content of the character string is arbitrary as well as the character string “idea”. Note that the character string here means that the shape of the handwriting is a character string, unlike text consisting of a series of character codes. Reference numeral 21 indicates a one-stroke mark query. This is, for example, a star that has been input by handwriting (or selected in a handwritten document). For example, the one-stroke mark is added to distinguish a portion where the degree of attention of the user is different from others. In some cases, a handwritten document is written at the beginning of a line to be bulleted. Reference numeral 22 indicates an underlined query. The underline is often written to emphasize a character string in a handwritten document. Reference numeral 23 indicates an enclosing line query. The encircled line is often written in a handwritten document in order to emphasize a character string in the same manner as an underline, or to distinguish a specific character string from other character strings.
The query determination unit 2 determines the type of the query by determining the shape of the handwriting based on the handwriting coordinate data acquired by the acquisition unit 1. Specific processing for determining the type of query will be described later.

  A query input method will be described with reference to FIG. Query input methods include (i) direct handwriting, (ii) direct handwriting selection, and (iii) indirect handwriting selection.

  (I) Direct handwriting is a method in which a user manually inputs a handwriting as a query using an input device (such as a stylus pen) in search input. In FIG. 3, a directly handwritten query example 30 is a character string “idea”, the query example 31 is an asterisk one-stroke mark, and the query example 32 is underlined. Example 33 is a box line. Mainly, a search input area is presented, and a user directly inputs into the search input area for execution.

  (Ii) Direct handwriting selection is a method for directly selecting a handwriting to be a query in a displayed handwritten document, instead of handwriting input of the query itself as described above. For example, when the user operates the input device so as to draw the diagonal line 34, the handwriting 35 (in this example, “idea”) within the rectangle defined by the diagonal line 34 is directly selected. Alternatively, the handwriting 36 itself is directly selected by tapping with an input device or a finger.

  (Iii) Indirect handwriting selection is a method of indirectly selecting a handwriting to be a query in a displayed handwritten document. For example, when the user operates the input device to draw the underline 37, the upper handwriting 38 (“idea” in this example) adjacent to the underline 37 is indirectly selected. Alternatively, the handwriting 40 (in this example, “idea”) inside the surrounding line 39 is indirectly selected by operating the input device to draw the surrounding line 39.

  In the above (iii) indirect handwriting selection, it is shown that the user operates the input device to draw the underline 37 for query input, but the query determination unit 2 determines the direction of the handwriting when the underline 37 is drawn. However, the processing of the underline 37 may be varied depending on the result. The direction of the handwriting can be determined from the magnitude relationship of the coordinate values in the time series of the handwriting data described above. For example, as shown in FIG. 4A, when the underline 37 is written in the direction from the left to the right of the page, it is not used as a query input, but is used as a normal underline handwriting (handwriting which is not a query). . On the other hand, as shown in FIG. 4B, when the underline 37 is written in the direction from the right to the left of the page, this is handled as a query input. Specifically, as described with reference to FIG. 3, the upper handwriting 42 (“idea” in this example) adjacent to the underline 37 is indirectly selected. Note that the direction of the handwriting may be similarly determined for other handwriting such as a surrounding line. For example, in the case of an encircling line written in a clockwise direction as a normal handwriting and an encircling line written in a counterclockwise direction, it may be determined that the selection is indirect handwriting as described with reference to FIG. . In this way, by changing the processing according to the direction determination of the handwriting, the user interface for handwriting search can be appropriately configured.

  A specific process for determining the type of query will be described with reference to the flowchart of FIG.

  In step S1, the shape of the input handwriting is determined. The query determination unit 2 determines the shape of the handwriting based on the coordinate data included in the handwriting data of the query input acquired by the acquisition unit 1, thereby determining the type of the query as a character string, a single stroke mark, an underline, an enclosure Determine to one of the lines.

  FIG. 6 is a flowchart showing the shape determination process. The shape determination process is performed based on handwriting coordinate data acquired by the acquisition unit 1.

In step S11 of FIG. 6, it is determined whether the input query (input handwriting) is a single stroke or multiple strokes. In the case of “one stroke”, it is determined in step S12 whether or not the stroke of the one stroke constitutes a closed loop. The closed loop determination process will be described with reference to FIG. Plot lines P ₁ , P ₂ ,. . It is determined whether P _n−1 and P _n are closed curves. Each line segment of the broken line is represented by L _i = P _i P _{i + 1} . At this time, it is checked whether L _i and L _j (i <j) intersect. If they intersect, P [i],. . . It is determined that P [j + 1] constitutes a closed curve. For example, in the example of FIG. 7, line segments L [2] and L [7] intersect, and P [2],. . , P [8] constitute a closed curve. Further, the distance from the start point to the end point of the stroke is calculated. If this is smaller than the total length of the stroke, it is determined that the loop is closed. If it is determined in step S12 in FIG. 6 that the loop is closed, it is determined in step 15 whether or not handwriting is included inside the closed loop.

  Processing for determining whether or not handwriting is included inside the closed loop will be described with reference to FIG. When each point Q [1], Q [2],..., Q [M] of the handwriting to be determined is within the closed loop curve, it is determined that the handwriting is included in the closed loop. Whether or not the point Q is included in the closed loop can be determined as follows. P [1] (X [1], Y [1]), P [2] (X [2], Y [2]),..., P [N-1] (X [N-1]) , Y [N−1]), and the point to be determined is Q (X, Y).

(1) A straight line f [i] (x, y) = 0 passing through two points P [i] and P [i + 1]
f (x, y) = (Y [i + 1] −Y [i]) * (x−X [i]) − (X [i + 1] −X [i]) * (y−Y [i]) = 0
Calculate as However, when i = N, the straight line f [N] (x, y) = 0 passing through the two points P [N] and P [0].

(2) It is determined which side Q (X, Y) is on the straight line traveling direction. Therefore, f [i] (X, Y) is calculated. If this value is positive, it is on the right side of the straight line direction, and if it is negative, it is on the left side.

(3) Repeat (1) and (2) above for all i, and if Q (X, Y) takes the same sign for all straight lines f [i] (X, Y), then Q is inside the closed loop Is determined.

  If it is determined in step S15 that the loop is closed, it is determined that the type of query is “border”.

  If the closed loop is not determined in step S12 or step S15, it is determined in step S13 whether the handwriting of the one stroke is a horizontal line. For example, a known linear regression problem is solved and a broken line is fitted with a straight line. If the regression error obtained by the processing is within the threshold, it is determined as a straight line. If it can be determined that the line is straight, it is determined to be in the horizontal direction if the absolute value of the inclination of the line is equal to or less than a certain value. If it is determined in step S13 that the line is a horizontal line, it is determined in step 16 whether or not there is a handwriting near the top of the horizontal line.

  Processing for determining whether or not there is a handwriting near the top of the horizontal line will be described with reference to FIG.

  When each point Q [1], Q [2],..., Q [M] of the handwriting to be determined is near the upper part of the line segment, it is determined that there is a handwriting near the upper part of the line segment. Whether or not there is a point Q near the top of the line segment can be determined as follows. The line segment is P [1] (X [1], Y [1]), P [2] (X [2], Y [2]), where X [1] <X [2] Let Q (X, Y) be the point. When the following four expressions are satisfied at the same time, it can be determined that there is a point Q near the top of the line segment.

X [1] <X
X <X [2]
Y> (Y [1] + Y [2]) / 2
Y <(Y [1] + Y [2]) / 2 + C
However, C is a predetermined threshold value.

If it is determined in step S16 that there is a handwriting near the top of the horizontal line, it is finally determined that the type of query is “underline”.

  If it is not determined that the line is a horizontal line in step S13 or step S16, it is determined in step S14 whether the handwriting of the one stroke is a mark. In this case, the degree of similarity between the one-stroke handwriting and a predetermined mark (eg, “◯”, “Δ”, “☆”, “□”) is calculated. If the degree of similarity with each mark is equal to or less than a certain value, it is determined that the mark is a “1-stroke mark”. For example, a method described in Japanese Patent No. 3537949 may be used as a specific process for calculating the similarity with a predetermined mark.

  If it is not determined as a mark in step S14 of FIG. 6 and if it is determined as “multiple images” in step S11, the type of query is determined as “character string”.

  In step S2 of FIG. 5, it is determined whether the query input method is “direct writing” or “selection” (refer to FIG. 3 for the query input method). In the case of “direct writing”, the input handwriting data is output as a query together with the determined query type. In the case of “selection”, handwriting data is extracted by selecting a region to be a query from the displayed handwritten document, and is output together with the determined type of query.

  The query type and handwriting data determined as described above are passed from the query determination unit 2 to the search unit 3 and the search result display unit 5.

  Next, the search processing start timing will be described. The search process according to the present embodiment can execute a search in each of the scenes of (i) direct handwriting, (ii) direct handwriting selection, and (iii) indirect handwriting selection. (I) In the case of direct handwritten writing, a search process is executed when a search button is selected with a pen after writing. This is similar to a series of operations in which a search button is clicked with a mouse after text input during text search. When the search input area is presented, the input handwriting may be used as a handwriting to be searched when pen-up or when there is no input for a predetermined time.

  (Ii) In the case of direct handwriting selection, the following is executed when it is determined that the query handwriting is selected.

  (1) A search process is executed at the time of pen-up (mainly in the search mode).

Or
(2) Display a context menu or a dialog at the time of pen-up and confirm whether to perform a search to the user.

  (Iii) In the case of indirect handwriting selection, when it is determined that the query handwriting has been selected, the same operation as in (ii) above is performed.

The search unit 3 obtains a search result by searching a document from the handwritten document DB 4 according to a search method according to the type of query determined by the query determination unit 2. Specifically, the search is performed according to a search method corresponding to the type of query as follows.
(A) Character string: The handwritten document DB 4 is searched for a handwriting that is similar to or matches the query for the character string.
(B) Single stroke mark: A handwriting similar to or matching with the single stroke mark query is searched in the handwritten document DB 4. However, if the one-stroke mark is selected from the beginning of the line, the search target may be limited to the beginning of the line or the priority of the mark at the beginning of the line may be increased.
(C) Underline: In the handwritten document DB 4, a horizontal line adjacent to the handwriting on the upper side is searched.
(D) Enclosed line: In the handwritten document DB 4, a closed curve including a handwriting inside is searched.
Here, a specific example of processing for searching the handwritten document DB 4 for a handwriting similar to or matching a character string query will be described. The search unit 3 searches for a stroke sequence similar to the stroke sequence representing the handwriting of the query, for example, by matching feature vectors. An example of a more specific structure of stroke data (handwriting data) will be described with reference to FIG.

  A “stroke” is a handwritten input stroke and represents a trajectory from when the pen or the like touches the input surface until it leaves. Usually, since points on the trajectory are sampled at a predetermined timing (for example, at a constant period), the stroke is expressed by a series of sampled points.

  In the example of FIG. 8B, the stroke structure for one stroke (that is, one fraction) is expressed by a set of coordinate values (point structure) on the plane on which the pen has moved. Is a structure including an array of “point structure” indicating the number of points forming “number of points”, “start time”, “circumscribed figure”, and a number of “point structures” corresponding to the total number of points. Here, the start time indicates the time when the pen is written in contact with the input surface in the stroke. The circumscribed figure indicates a circumscribed figure (preferably, a rectangle with the smallest area that includes the stroke on the document plane) with respect to the locus of the stroke on the document plane.

  The point structure may depend on the input device. In the example of FIG. 8C, the structure of one point has a coordinate value x, y at which the point is sampled, a writing pressure, and a four-value difference of time from an initial point (for example, the above “start time”). Is the body.

  Note that the coordinates are a coordinate system of the document plane, and may be expressed as a positive value whose value becomes larger as it goes to the lower right corner as the origin of the upper left corner.

  In addition, when the input device cannot acquire the writing pressure, or when the writing pressure can be acquired but the writing pressure is not used in the subsequent processing, the writing pressure in FIG. 8C may be omitted or the writing pressure may be reduced. Data indicating invalidity may be described.

  In the example of FIGS. 8B and 8C, actual data such as coordinate values x and y may be described in the area of each point structure in the stroke structure, or the data of the stroke structure and As information for managing point structure data separately, link information to the corresponding point structure may be described in the area of each point structure in the stroke structure.

  For example, DP matching (DP; Dynamic Programming) may be used as a specific example of feature vector matching when searching for a stroke sequence similar to a stroke sequence representing the handwriting of a query. Note that the number of strokes specified by the user and the number of strokes desired by the user may not necessarily be the same. This is because, for example, some writers may write two strokes of the same character in one stroke, and even a character string having the same meaning may be written with a different number of strokes depending on the writer. It is. Normally, DP matching related to strokes is a method that handles only one-to-one stroke correspondence and performs an optimum association that allows expansion and contraction between two stroke sequences. Therefore, for example, by using DP matching that also takes into account the correspondence between 1 stroke and N stroke, it is possible to perform robust matching against stroke variations (for example, “DP in Masuda, Uchida, Sakoe, Online Character Recognition”). (See Matching experimental optimization, Electrical Engineering Society Kyushu Branch Association, H.17. Http://human.ait.kyushu-u.ac.jp/~uchida/Papers/masuda-shibu2005.pdf ”).

  For example, after associating with all strokes included in a stroke sequence to be matched as a starting point, a stroke sequence which is a query designated by the user, the similarity between the stroke sequences is calculated. And after calculating the similarity from each starting point, it sorts in descending order. Since all strokes are the starting points, overlapping results are obtained. Thereafter, peak detection is performed to integrate the overlapping stroke ranges.

  In addition to the above, various matching methods are possible.

The search result display unit 5 displays the search result obtained by the search unit 3 by a display method according to the type of query. As a result display method for each type of query, the following two patterns of display methods can be considered.
(1) Display the searched handwriting and the handwriting close to the search handwriting.

  (2) One page of handwriting including the searched handwriting is displayed.

In both cases, however, it is preferable to change the highlighting method according to the type of query as follows.
(A) Character string: Displayed including a handwriting close to the search handwriting. However, the searched handwriting itself is highlighted by changing the color.
(B) Single stroke mark: Displayed including a handwriting close to the search handwriting. However, the searched handwriting itself and the handwriting for one line following it are highlighted by changing the color or the like.

  (C) Underline: A handwriting close to the search handwriting is included and displayed. However, the retrieved handwriting itself and the handwriting adjacent thereto are highlighted by changing the color.

  (D) Surrounding line: The search handwriting is displayed including the handwriting adjacent to it. However, the searched handwriting itself and the handwriting contained therein are highlighted by changing the color or the like.

  FIG. 9 shows a display example of search results. FIG. 9A shows an example in which a search result 82 including a proximity handwriting in a search handwriting (character string) 81 is displayed in a window 80 showing the search result. FIG. 9B shows an example in which, on the page 83 including the searched handwriting, a one-line mark 85 and one line of handwriting 86 including the handwriting following the one-stroke mark 85 are displayed.

  According to the embodiment described below, it is possible to determine the type of handwritten query, execute a search by a search method according to the type of handwritten query, and display the search result by an appropriate display method according to this. Therefore, an accurate search can be performed by a search method corresponding to the type of query.

  Hereinafter, variations of the present embodiment will be described.

  The search unit 3 of the present embodiment may search for a handwritten document group stored in the handwritten document DB 4 inside the document search device, and the document search device can be connected to a network such as an intranet and / or the Internet. In some cases, a group of handwritten documents accessible via a network may be searched, a group of handwritten documents stored in a removable memory connected to the document search apparatus may be searched, Any combination may be used.

  The document search apparatus according to the present embodiment can be configured as a stand-alone apparatus or can be configured in a distributed form among a plurality of nodes that can communicate via a network.

  In addition, the document search apparatus according to the present embodiment includes a desktop or laptop general-purpose computer, a portable general-purpose computer, other portable information devices, information devices having a touch panel, smartphones, other information processing devices, and the like. It can be realized by various devices.

  FIG. 10 shows a configuration example of hardware that realizes the document search apparatus according to the present embodiment. In the figure, 201 is a CPU, 202 is a predetermined input device, 203 is a predetermined output device, 204 is a RAM, 205 is a ROM, 206 is an external memory interface, and 207 is a communication interface. For example, when a touch panel is used, for example, a liquid crystal panel, a pen, and a stroke detection device provided on the liquid crystal panel are used (see 208 in the figure).

  Further, for example, a part of the configuration of FIG. 1 can be provided on the client, and the remaining part of the configuration of FIG. 1 can be provided on the server.

  For example, FIG. 11 shows that the server 303 exists on a network 300 such as an intranet and / or the Internet, and the clients 301 and 302 communicate with the server 303 via the network 300, respectively. This illustrates how this is realized.

  Note that the client 301 is connected to the network 300 via wireless communication, and the client 302 is connected to the network 302 via wired communication.

  The clients 301 and 302 are usually user devices. For example, the server 303 may be provided on a LAN such as a corporate LAN or may be operated by an Internet service provider or the like. Further, the server 303 may be a user device, and a certain user may provide functions to other users.

  Various methods can be considered as a method of distributing the configuration of FIG. 1 to the client and the server.

The instructions shown in the processing procedure shown in the above embodiment can be executed based on a program that is software. The general-purpose computer system stores this program in advance and reads this program, so that it is possible to obtain the same effect as that obtained by the document search apparatus of the above-described embodiment. The instructions described in the above-described embodiments are, as programs that can be executed by a computer, magnetic disks (flexible disks, hard disks, etc.), optical disks (CD-ROM, CD-R, CD-RW, DVD-ROM, DVD). ± R, DVD ± RW, etc.), semiconductor memory, or a similar recording medium. As long as the recording medium is readable by the computer or the embedded system, the storage format may be any form. If the computer reads the program from the recording medium and causes the CPU to execute instructions described in the program based on the program, the same operation as that of the document search apparatus of the above-described embodiment can be realized. Of course, when the computer acquires or reads the program, it may be acquired or read through a network.
In addition, the OS (operating system), database management software, MW (middleware) such as a network, etc. running on the computer based on the instructions of the program installed in the computer or embedded system from the recording medium implement this embodiment. A part of each process for performing may be executed.
Furthermore, the recording medium in the present embodiment is not limited to a medium independent of a computer or an embedded system, but also includes a recording medium in which a program transmitted via a LAN, the Internet, or the like is downloaded and stored or temporarily stored.
Further, the number of recording media is not limited to one, and when the processing in this embodiment is executed from a plurality of media, it is included in the recording medium in this embodiment, and the configuration of the media may be any configuration.

The computer or the embedded system in the present embodiment is for executing each process in the present embodiment based on a program stored in a recording medium. The computer or the embedded system includes a single device such as a personal computer or a microcomputer. The system may be any configuration such as a system connected to the network.
In addition, the computer in this embodiment is not limited to a personal computer, but includes an arithmetic processing device, a microcomputer, and the like included in an information processing device, and is a generic term for devices and devices that can realize the functions in this embodiment by a program. ing.

  Although several embodiments of the present invention have been described, these embodiments are presented by way of example and are not intended to limit the scope of the invention. These novel embodiments can be implemented in various other forms, and various omissions, replacements, and changes can be made without departing from the scope of the invention. These embodiments and modifications thereof are included in the scope and gist of the invention, and are included in the invention described in the claims and the equivalents thereof.

  DESCRIPTION OF SYMBOLS 1 ... Acquisition part, 2 ... Query determination part, 3 ... Search part, 4 ... Handwritten document database (DB), 5 ... Search result display part.

Claims (12)

An acquisition means for acquiring handwriting data including coordinate data;
Based on the coordinate data, character strings, Ichikaku mark, underlining, classifies the types of queries that contain one of the encircling line, search that searches a document according to the search method corresponding to the type of the query Means ,
Ru with a document retrieval apparatus. If the query type is the character string, search for a handwriting in a handwritten document similar to the handwriting,
If the query type is a one-stroke mark, the handwriting at the beginning of the line in the handwritten document similar to the handwriting is searched with high priority,
If the type of query is underlined, search for a horizontal line in the handwritten document with handwriting adjacent on the upper side,
The apparatus according to claim 1, wherein when the type of the query is an encircling line, a closed curve in the handwritten document including a handwriting is searched. Comprising the further display means for displaying a search result of a search according to the search method in accordance with the type,
The apparatus according to claim 1, wherein the search result is highlighted according to a type of the query. Comprising the further display means for displaying a search result of a search according to the search method in accordance with the type,
The apparatus according to claim 1, wherein the search result includes a type of the query and a handwriting including the searched search result. An acquisition means for acquiring handwriting data including coordinate data; and
Search means, based on the coordinate data, character strings, Ichikaku mark, classified into types of queries, including underline, any one of the encircling line, searching a document according to the search method corresponding to the type of the query and to Luz step, document retrieval method Ru equipped with. If the query type is the character string, search for a handwriting in a handwritten document similar to the handwriting,
If the query type is a one-stroke mark, the handwriting at the beginning of the line in the handwritten document similar to the handwriting is searched with high priority,
If the type of query is underlined, search for a horizontal line in the handwritten document with handwriting adjacent on the upper side,
The method according to claim 5, wherein, when the type of the query is a surrounding line, a closed curve in the handwritten document that includes a handwriting is searched. Display means, further to comprising the step of displaying the search result of a search according to the search method in accordance with the type,
The method according to claim 5, wherein the search result is highlighted according to a type of the query. Display means, further to comprising the step of displaying the search result of a search according to the search method in accordance with the type,
The method according to claim 5, wherein the search result includes a type of the query and a handwriting including the searched search result. Computer
Acquisition means for acquiring handwriting data including coordinate data;
Based on the coordinate data, character strings, Ichikaku mark, underlining, classifies the types of queries that contain one of the encircling line, search that searches a document according to the search method corresponding to the type of the query Means ,
Program to function as. If the query type is the character string, search for a handwriting in a handwritten document similar to the handwriting,
If the query type is a one-stroke mark, the handwriting at the beginning of the line in the handwritten document similar to the handwriting is searched with high priority,
If the type of query is underlined, search for a horizontal line in the handwritten document with handwriting adjacent on the upper side,
The program according to claim 9, wherein when the type of the query is an encircling line, a closed curve in the handwritten document that includes a handwriting is searched. Further function as a display means for displaying a search result searched according to the search method according to the type,
The program according to claim 9, wherein the search result is highlighted according to the type of the query. Further function as a display means for displaying a search result searched according to the search method according to the type,
The program according to claim 9, wherein as the search result, a type of the query and a handwriting including the searched search result are displayed.

Images